A general-purpose multi-agent framework built on LangGraph. Features KV Cache-preserving summarization, long-term memory (BGE-M3 + pgvector), and four specialized sub-agents: Map, Weather, Railway, and Web Search.
- capability exposure inferred + 24
- recent drift inferred + 12
- tool safety inferred + 12
inferred
The A–E grade is our heuristic synthesis — a "review this" prompt, not a verdict. Each factor is tagged by what backs it: attested (a verifiable record), reported (a third party's claim), or inferred (our own heuristic, e.g. permissions). See methodology.
grade last moved 18h ago · see ecosystem CVEs →
- C · 56 → C · 48
- C · 48 → C · 56
No known CVEs for this server.
- high dangerous code
committed secret: committed .env
analyzed commit 86614e4 · analyzer v33 · 3w ago
danger signals1
- committed secret committed .env ColtM1873-LangGraph-General-Use-Multi-Agent-Framework-86614e4/.env :1
env file shipped with populated values
- recent drift +12 capability drift →
[](https://mcpobservatory.com/servers/github:ColtM1873/LangGraph-General-Use-Multi-Agent-Framework/security) Heuristic, inferred signals — false positives (legitimately powerful tools, forks, language ports) are expected. Treat each as "review this", not a verdict. See the ecosystem-wide picture on the security hub, or the fleet security of ColtM1873.